Fake Healthcare Experts
Notes, experiments, and documentation
How the AI revolution is quietly outsourcing your brain — and what to do about it. From the ClickFix paste-and-run attack to hallucinating models that sound most certain when they're most wrong.
Setting up ClawdBot (also known as Moltbot) on a Raspberry Pi 3 — exploring AI API cost alternatives including Venice AI credit staking and Claude Pro subscriptions, and whether a Claude Code subscription can run the raptor personality to avoid churning raw API tokens.
Traditional vulnerabilities still account for 78% of successful exploitations, yet bounty payouts for AI bugs have jumped 340%. Are researchers chasing money instead of risk?
A purely analog Simple Add-On for DEF CON — a 555 timer driving a CD4017 decade counter that chases eight LEDs across a custom 60mm × 60mm PCB. No microcontroller, no firmware. Just power and ground.
A deep dive into prompt injection techniques, jailbreaks, and vulnerabilities — from basic instruction overrides to recursive multi-model exploits. Covers 12 attack patterns including role-play jailbreaks, context overflow, cognitive hacking, and the defined dictionary attack.